Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

It’s so hard to finish an idea that is not yours and is just suggested by AI

ssp.sh

Post reply on HN
Print view View original

141–150 of 159 posts

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#141

Post by killix »

t-writescode wrote: post #131
synalx wrote: post #3

I have this problem even in codebases. Claude will work on something, and add detailed comments in which it extrapolates the from the design and confidently states intentions and decisions which aren't actually grounded in reality. Then, later sessions suffer when it reads back those hallucinations and treats them as canonical.

So, I admit that I'm finally getting into this "let Claude help you write code" stuff, and I'm enjoying it a bit for the stuff I, honestly, just don't want to write; but ... I still read it. I still review it. I still look at the code like I'm peer-reviewing it and go, "Uh ... I don't like this area at all. That's going to be really hard to debug at 3am" and so on. I guess my thought / question is: this is your code.…

[flagged]

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#142

Post by menaerus »

cs02rm0 wrote: post #140
t-writescode wrote: post #131

Earlier quoted context omitted.

So, I admit that I'm finally getting into this "let Claude help you write code" stuff, and I'm enjoying it a bit for the stuff I, honestly, just don't want to write; but ... I still read it. I still review it. I still look at the code like I'm peer-reviewing it and go, "Uh ... I don't like this area at all. That's going to be really hard to debug at 3am" and so on. I guess my thought / question is: this is your code.…

> So, I admit that I'm finally getting into this "let Claude help you write code" stuff, and I'm enjoying it a bit for the stuff I, honestly, just don't want to write; but ... I still read it. I still review it. I still look at the code like I'm peer-reviewing it and go, "Uh ... I don't like this area at all. That's going to be really hard to debug at 3am" and so on. I used to. I've stopped in recent months, only bec…

Exactly. That would mean going back to square one, and I also personally don't review the code anymore but I am more focused on asking the model to demonstrate the value it created through benchmarks, workload-generators, and e2e tests.

Mostly it proves as a valid approach, barring the bugs the model can introduce to value-demonstrating benchmarks which can of course skew the evidence on hypotheses, and thus code trajectory the model opts to go with.

The problem I see with this is really that I am not anymore under the control but I am not sure I see other alternative. I am becoming more and more like a system observer with surface-level understanding of the system rather than the engineer with zoomed-in level of understanding of how the code actually behaves. Perhaps we're transitioning into a QA roles present.

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#143

Post by t-writescode »

cs02rm0 wrote: post #140
t-writescode wrote: post #131

Earlier quoted context omitted.

So, I admit that I'm finally getting into this "let Claude help you write code" stuff, and I'm enjoying it a bit for the stuff I, honestly, just don't want to write; but ... I still read it. I still review it. I still look at the code like I'm peer-reviewing it and go, "Uh ... I don't like this area at all. That's going to be really hard to debug at 3am" and so on. I guess my thought / question is: this is your code.…

> So, I admit that I'm finally getting into this "let Claude help you write code" stuff, and I'm enjoying it a bit for the stuff I, honestly, just don't want to write; but ... I still read it. I still review it. I still look at the code like I'm peer-reviewing it and go, "Uh ... I don't like this area at all. That's going to be really hard to debug at 3am" and so on. I used to. I've stopped in recent months, only bec…

Why? You own the pager, I assume. You own the mental hit when something you let go live (especially with your name on the PR) leaks customer data or deleted someone’s work.

And if you’re not reading your own work, is someone else during the PR? Are you reading other people’s PRs?

How do you know what your product does and how it does it?

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#144

Post by justbees »

sdeframond wrote: post #49
post-it wrote: post #46

Earlier quoted context omitted.

I've been whittling my way towards having Claude write zero comments in code. They're pretty much never helpful.

How do you do it?

I include a rule in the initial PR prep that it runs. So there's a hard limit to the length of the comments and what type of comments it can write and they get flagged in the review. It also reads the comments and checks for consistency with the following code so they don't drift. And the reviewer is a completely different agent/different model.

So all of that happens before the manual review and usually catches a lot of the 3-5 line comments it inevitably adds.

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#145

Post by p0w3n3d »

synalx wrote: post #3

I have this problem even in codebases. Claude will work on something, and add detailed comments in which it extrapolates the from the design and confidently states intentions and decisions which aren't actually grounded in reality. Then, later sessions suffer when it reads back those hallucinations and treats them as canonical.

In numerical methods this is called error propagation. And since the neural networks are basically numerical approximations of a certain function, this shows apparent similarity of the propagation on a macro scale

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#146

Post by menaerus »

t-writescode wrote: post #143
cs02rm0 wrote: post #140

Earlier quoted context omitted.

> So, I admit that I'm finally getting into this "let Claude help you write code" stuff, and I'm enjoying it a bit for the stuff I, honestly, just don't want to write; but ... I still read it. I still review it. I still look at the code like I'm peer-reviewing it and go, "Uh ... I don't like this area at all. That's going to be really hard to debug at 3am" and so on. I used to. I've stopped in recent months, only bec…

Why? You own the pager, I assume. You own the mental hit when something you let go live (especially with your name on the PR) leaks customer data or deleted someone’s work. And if you’re not reading your own work, is someone else during the PR? Are you reading other people’s PRs? How do you know what your product does and how it does it?

When the combustion engine was invented, and we got the means by which we could accelerate our trip by 10x, and at the same time scale it to multiple people, we didn't tell the humans to keep pushing the vehicles by their hands, didn't we?

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#147

Post by huurtehoog »

Dependance wrote: post #32

Could anyone enlighten me as to why to use Obsidian in one's daily life ? I have a dozen ideas popping a day and nothing comes close in terms of ease than a paper notebook for capturing and some apple notes equivalent for storage. Used to have a Notion but all the "Second Brain" movement seems...fishy to me ?

Self soothing behavior. Helps quell the anxiety derived from the dopamine threadmill of modern digital media.

We're all becoming mental hoarders and discussing our piles of though junk in our digital storage units.

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#148

Post by Cameri »

altairprime wrote: post #40

Ironically, this is why one of the best ways to manage upwards is to prompt managers into coming up with your idea as if it were their own: they’re dramatically more likely to execute and deliver on it. Of course, this also obviously leads to undue credit given for coming up the idea, which is certainly a core problem with AI as well, but it’s still charming to watch managerial psych being rediscovered by this new ge…

Nothing beats the feeling of having a proposed idea dismissed just to have the higher ups “come up” with it some time later. Don’t even dream about getting a footnote mention.

Re: It’s so hard to finish an idea that is not yours and is just suggested by AI

#149

Post by defrost »

menaerus wrote: post #146
t-writescode wrote: post #143

Earlier quoted context omitted.

Why? You own the pager, I assume. You own the mental hit when something you let go live (especially with your name on the PR) leaks customer data or deleted someone’s work. And if you’re not reading your own work, is someone else during the PR? Are you reading other people’s PRs? How do you know what your product does and how it does it?

When the combustion engine was invented, and we got the means by which we could accelerate our trip by 10x, and at the same time scale it to multiple people, we didn't tell the humans to keep pushing the vehicles by their hands, didn't we?

No, but the US and UK did enact Red Flag laws.
Post reply on HN